April 3, 2020

2810 words 14 mins read

Paper Group ANR 41

Paper Group ANR 41

Predicting Personalized Academic and Career Roads: First Steps Toward a Multi-Uses Recommender System. Improved Robust ASR for Social Robots in Public Spaces. How Good is the Bayes Posterior in Deep Neural Networks Really?. A Better Variant of Self-Critical Sequence Training. A Lobster-inspired Robotic Glove for Hand Rehabilitation. On the Resilien …

Predicting Personalized Academic and Career Roads: First Steps Toward a Multi-Uses Recommender System

Title Predicting Personalized Academic and Career Roads: First Steps Toward a Multi-Uses Recommender System
Authors Alexandre Nadjem, Juan-Manuel Torres-Moreno, Marc El-Bèze, Guillaume Marrel, Benoît Bonte
Abstract Nobody knows what one’s do in the future and everyone will have had a different answer to the question : how do you see yourself in five years after your current job/diploma? In this paper we introduce concepts, large categories of fields of studies or job domains in order to represent the vision of the future of the user’s trajectory. Then, we show how they can influence the prediction when proposing him a set of next steps to take.
Tasks Recommendation Systems
Published 2020-01-03
URL https://arxiv.org/abs/2001.10613v1
PDF https://arxiv.org/pdf/2001.10613v1.pdf
PWC https://paperswithcode.com/paper/predicting-personalized-academic-and-career

Improved Robust ASR for Social Robots in Public Spaces

Title Improved Robust ASR for Social Robots in Public Spaces
Authors Charles Jankowski, Vishwas Mruthyunjaya, Ruixi Lin
Abstract Social robots deployed in public spaces present a challenging task for ASR because of a variety of factors, including noise SNR of 20 to 5 dB. Existing ASR models perform well for higher SNRs in this range, but degrade considerably with more noise. This work explores methods for providing improved ASR performance in such conditions. We use the AiShell-1 Chinese speech corpus and the Kaldi ASR toolkit for evaluations. We were able to exceed state-of-the-art ASR performance with SNR lower than 20 dB, demonstrating the feasibility of achieving relatively high performing ASR with open-source toolkits and hundreds of hours of training data, which is commonly available.
Published 2020-01-14
URL https://arxiv.org/abs/2001.04619v1
PDF https://arxiv.org/pdf/2001.04619v1.pdf
PWC https://paperswithcode.com/paper/improved-robust-asr-for-social-robots-in

How Good is the Bayes Posterior in Deep Neural Networks Really?

Title How Good is the Bayes Posterior in Deep Neural Networks Really?
Authors Florian Wenzel, Kevin Roth, Bastiaan S. Veeling, Jakub Świątkowski, Linh Tran, Stephan Mandt, Jasper Snoek, Tim Salimans, Rodolphe Jenatton, Sebastian Nowozin
Abstract During the past five years the Bayesian deep learning community has developed increasingly accurate and efficient approximate inference procedures that allow for Bayesian inference in deep neural networks. However, despite this algorithmic progress and the promise of improved uncertainty quantification and sample efficiency there are—as of early 2020—no publicized deployments of Bayesian neural networks in industrial practice. In this work we cast doubt on the current understanding of Bayes posteriors in popular deep neural networks: we demonstrate through careful MCMC sampling that the posterior predictive induced by the Bayes posterior yields systematically worse predictions compared to simpler methods including point estimates obtained from SGD. Furthermore, we demonstrate that predictive performance is improved significantly through the use of a “cold posterior” that overcounts evidence. Such cold posteriors sharply deviate from the Bayesian paradigm but are commonly used as heuristic in Bayesian deep learning papers. We put forward several hypotheses that could explain cold posteriors and evaluate the hypotheses through experiments. Our work questions the goal of accurate posterior approximations in Bayesian deep learning: If the true Bayes posterior is poor, what is the use of more accurate approximations? Instead, we argue that it is timely to focus on understanding the origin of the improved performance of cold posteriors.
Tasks Bayesian Inference
Published 2020-02-06
URL https://arxiv.org/abs/2002.02405v1
PDF https://arxiv.org/pdf/2002.02405v1.pdf
PWC https://paperswithcode.com/paper/how-good-is-the-bayes-posterior-in-deep

A Better Variant of Self-Critical Sequence Training

Title A Better Variant of Self-Critical Sequence Training
Authors Ruotian Luo
Abstract In this work, we present a simple yet better variant of Self-Critical Sequence Training. We make a simple change in the choice of baseline function in REINFORCE algorithm. The new baseline can bring better performance with no extra cost, compared to the greedy decoding baseline.
Published 2020-03-22
URL https://arxiv.org/abs/2003.09971v1
PDF https://arxiv.org/pdf/2003.09971v1.pdf
PWC https://paperswithcode.com/paper/a-better-variant-of-self-critical-sequence

A Lobster-inspired Robotic Glove for Hand Rehabilitation

Title A Lobster-inspired Robotic Glove for Hand Rehabilitation
Authors Yaohui Chen, Sing Le, Qiao Chu Tan, Oscar Lau, Fang Wan, Chaoyang Song
Abstract This paper presents preliminary results of the design, development, and evaluation of a hand rehabilitation glove fabricated using lobster-inspired hybrid design with rigid and soft components for actuation. Inspired by the bending abdomen of lobsters, hybrid actuators are built with serially jointed rigid shells actuated by pressurized soft chambers inside to generate bending motions. Such bio-inspiration absorbs features from the classical rigid-bodied robotics with precisely-defined motion generation, as well as the emerging soft robotics with light-weight, physically safe, and adaptive actuation. The fabrication procedure is described, followed by experiments to mechanically characterize these actuators. Finally, an open-palm glove design integrated with these hybrid actuators is presented for a qualitative case study. A hand rehabilitation system is developed by learning patterns of the sEMG signals from the user’s forearm to train the assistive glove for hand rehabilitation exercises.
Published 2020-03-01
URL https://arxiv.org/abs/2003.00577v1
PDF https://arxiv.org/pdf/2003.00577v1.pdf
PWC https://paperswithcode.com/paper/a-lobster-inspired-robotic-glove-for-hand

On the Resilience of Biometric Authentication Systems against Random Inputs

Title On the Resilience of Biometric Authentication Systems against Random Inputs
Authors Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Mohamed Ali Kaafar
Abstract We assess the security of machine learning based biometric authentication systems against an attacker who submits uniform random inputs, either as feature vectors or raw inputs, in order to find an accepting sample of a target user. The average false positive rate (FPR) of the system, i.e., the rate at which an impostor is incorrectly accepted as the legitimate user, may be interpreted as a measure of the success probability of such an attack. However, we show that the success rate is often higher than the FPR. In particular, for one reconstructed biometric system with an average FPR of 0.03, the success rate was as high as 0.78. This has implications for the security of the system, as an attacker with only the knowledge of the length of the feature space can impersonate the user with less than 2 attempts on average. We provide detailed analysis of why the attack is successful, and validate our results using four different biometric modalities and four different machine learning classifiers. Finally, we propose mitigation techniques that render such attacks ineffective, with little to no effect on the accuracy of the system.
Published 2020-01-13
URL https://arxiv.org/abs/2001.04056v2
PDF https://arxiv.org/pdf/2001.04056v2.pdf
PWC https://paperswithcode.com/paper/on-the-resilience-of-biometric-authentication

Spinal Metastases Segmentation in MR Imaging using Deep Convolutional Neural Networks

Title Spinal Metastases Segmentation in MR Imaging using Deep Convolutional Neural Networks
Authors Georg Hille, Johannes Steffen, Max Dünnwald, Mathias Becker, Sylvia Saalfeld, Klaus Tönnies
Abstract This study’s objective was to segment spinal metastases in diagnostic MR images using a deep learning-based approach. Segmentation of such lesions can present a pivotal step towards enhanced therapy planning and validation, as well as intervention support during minimally invasive and image-guided surgeries like radiofrequency ablations. For this purpose, we used a U-Net like architecture trained with 40 clinical cases including both, lytic and sclerotic lesion types and various MR sequences. Our proposed method was evaluated with regards to various factors influencing the segmentation quality, e.g. the used MR sequences and the input dimension. We quantitatively assessed our experiments using Dice coefficients, sensitivity and specificity rates. Compared to expertly annotated lesion segmentations, the experiments yielded promising results with average Dice scores up to 77.6% and mean sensitivity rates up to 78.9%. To our best knowledge, our proposed study is one of the first to tackle this particular issue, which limits direct comparability with related works. In respect to similar deep learning-based lesion segmentations, e.g. in liver MR images or spinal CT images, our experiments showed similar or in some respects superior segmentation quality. Overall, our automatic approach can provide almost expert-like segmentation accuracy in this challenging and ambitious task.
Published 2020-01-08
URL https://arxiv.org/abs/2001.05834v2
PDF https://arxiv.org/pdf/2001.05834v2.pdf
PWC https://paperswithcode.com/paper/spinal-metastases-segmentation-in-mr-imaging

Recovery command generation towards automatic recovery in ICT systems by Seq2Seq learning

Title Recovery command generation towards automatic recovery in ICT systems by Seq2Seq learning
Authors Hiroki Ikeuchi, Akio Watanabe, Tsutomu Hirao, Makoto Morishita, Masaaki Nishino, Yoichi Matsuo, Keishiro Watanabe
Abstract With the increase in scale and complexity of ICT systems, their operation increasingly requires automatic recovery from failures. Although it has become possible to automatically detect anomalies and analyze root causes of failures with current methods, making decisions on what commands should be executed to recover from failures still depends on manual operation, which is quite time-consuming. Toward automatic recovery, we propose a method of estimating recovery commands by using Seq2Seq, a neural network model. This model learns complex relationships between logs obtained from equipment and recovery commands that operators executed in the past. When a new failure occurs, our method estimates plausible commands that recover from the failure on the basis of collected logs. We conducted experiments using a synthetic dataset and realistic OpenStack dataset, demonstrating that our method can estimate recovery commands with high accuracy.
Published 2020-03-24
URL https://arxiv.org/abs/2003.10784v1
PDF https://arxiv.org/pdf/2003.10784v1.pdf
PWC https://paperswithcode.com/paper/recovery-command-generation-towards-automatic

Trust in Data Science: Collaboration, Translation, and Accountability in Corporate Data Science Projects

Title Trust in Data Science: Collaboration, Translation, and Accountability in Corporate Data Science Projects
Authors Samir Passi, Steven J. Jackson
Abstract The trustworthiness of data science systems in applied and real-world settings emerges from the resolution of specific tensions through situated, pragmatic, and ongoing forms of work. Drawing on research in CSCW, critical data studies, and history and sociology of science, and six months of immersive ethnographic fieldwork with a corporate data science team, we describe four common tensions in applied data science work: (un)equivocal numbers, (counter)intuitive knowledge, (in)credible data, and (in)scrutable models. We show how organizational actors establish and re-negotiate trust under messy and uncertain analytic conditions through practices of skepticism, assessment, and credibility. Highlighting the collaborative and heterogeneous nature of real-world data science, we show how the management of trust in applied corporate data science settings depends not only on pre-processing and quantification, but also on negotiation and translation. We conclude by discussing the implications of our findings for data science research and practice, both within and beyond CSCW.
Published 2020-02-09
URL https://arxiv.org/abs/2002.03389v1
PDF https://arxiv.org/pdf/2002.03389v1.pdf
PWC https://paperswithcode.com/paper/trust-in-data-science-collaboration

Analyzing the Dependency of ConvNets on Spatial Information

Title Analyzing the Dependency of ConvNets on Spatial Information
Authors Yue Fan, Yongqin Xian, Max Maria Losch, Bernt Schiele
Abstract Intuitively, image classification should profit from using spatial information. Recent work, however, suggests that this might be overrated in standard CNNs. In this paper, we are pushing the envelope and aim to further investigate the reliance on spatial information. We propose spatial shuffling and GAP+FC to destroy spatial information during both training and testing phases. Interestingly, we observe that spatial information can be deleted from later layers with small performance drops, which indicates spatial information at later layers is not necessary for good performance. For example, test accuracy of VGG-16 only drops by 0.03% and 2.66% with spatial information completely removed from the last 30% and 53% layers on CIFAR100, respectively. Evaluation on several object recognition datasets (CIFAR100, Small-ImageNet, ImageNet) with a wide range of CNN architectures (VGG16, ResNet50, ResNet152) shows an overall consistent pattern.
Tasks Image Classification, Object Recognition
Published 2020-02-05
URL https://arxiv.org/abs/2002.01827v1
PDF https://arxiv.org/pdf/2002.01827v1.pdf
PWC https://paperswithcode.com/paper/analyzing-the-dependency-of-convnets-on

Robust $k$-means Clustering for Distributions with Two Moments

Title Robust $k$-means Clustering for Distributions with Two Moments
Authors Yegor Klochkov, Alexey Kroshnin, Nikita Zhivotovskiy
Abstract We consider the robust algorithms for the $k$-means clustering problem where a quantizer is constructed based on $N$ independent observations. Our main results are median of means based non-asymptotic excess distortion bounds that hold under the two bounded moments assumption in a general separable Hilbert space. In particular, our results extend the renowned asymptotic result of Pollard, 1981 who showed that the existence of two moments is sufficient for strong consistency of an empirically optimal quantizer in $\mathbb{R}^d$. In a special case of clustering in $\mathbb{R}^d$, under two bounded moments, we prove matching (up to constant factors) non-asymptotic upper and lower bounds on the excess distortion, which depend on the probability mass of the lightest cluster of an optimal quantizer. Our bounds have the sub-Gaussian form, and the proofs are based on the versions of uniform bounds for robust mean estimators.
Published 2020-02-06
URL https://arxiv.org/abs/2002.02339v1
PDF https://arxiv.org/pdf/2002.02339v1.pdf
PWC https://paperswithcode.com/paper/robust-k-means-clustering-for-distributions

When does the Tukey median work?

Title When does the Tukey median work?
Authors Banghua Zhu, Jiantao Jiao, Jacob Steinhardt
Abstract We analyze the performance of the Tukey median estimator under total variation (TV) distance corruptions. Previous results show that under Huber’s additive corruption model, the breakdown point is 1/3 for high-dimensional halfspace-symmetric distributions. We show that under TV corruptions, the breakdown point reduces to 1/4 for the same set of distributions. We also show that a certain projection algorithm can attain the optimal breakdown point of 1/2. Both the Tukey median estimator and the projection algorithm achieve sample complexity linear in dimension.
Published 2020-01-21
URL https://arxiv.org/abs/2001.07805v2
PDF https://arxiv.org/pdf/2001.07805v2.pdf
PWC https://paperswithcode.com/paper/when-does-the-tukey-median-work

NBDT: Neural-Backed Decision Trees

Title NBDT: Neural-Backed Decision Trees
Authors Alvin Wan, Lisa Dunlap, Daniel Ho, Jihan Yin, Scott Lee, Henry Jin, Suzanne Petryk, Sarah Adel Bargal, Joseph E. Gonzalez
Abstract Deep learning is being adopted in settings where accurate and justifiable predictions are required, ranging from finance to medical imaging. While there has been recent work providing post-hoc explanations for model predictions, there has been relatively little work exploring more directly interpretable models that can match state-of-the-art accuracy. Historically, decision trees have been the gold standard in balancing interpretability and accuracy. However, recent attempts to combine decision trees with deep learning have resulted in models that (1) achieve accuracies far lower than that of modern neural networks (e.g. ResNet) even on small datasets (e.g. MNIST), and (2) require significantly different architectures, forcing practitioners pick between accuracy and interpretability. We forgo this dilemma by creating Neural-Backed Decision Trees (NBDTs) that (1) achieve neural network accuracy and (2) require no architectural changes to a neural network. NBDTs achieve accuracy within 1% of the base neural network on CIFAR10, CIFAR100, TinyImageNet, using recently state-of-the-art WideResNet; and within 2% of EfficientNet on ImageNet. This yields state-of-the-art explainable models on ImageNet, with NBDTs improving the baseline by ~14% to 75.30% top-1 accuracy. Furthermore, we show interpretability of our model’s decisions both qualitatively and quantitatively via a semi-automatic process. Code and pretrained NBDTs can be found at https://github.com/alvinwan/neural-backed-decision-trees.
Published 2020-04-01
URL https://arxiv.org/abs/2004.00221v1
PDF https://arxiv.org/pdf/2004.00221v1.pdf
PWC https://paperswithcode.com/paper/nbdt-neural-backed-decision-trees

3dDepthNet: Point Cloud Guided Depth Completion Network for Sparse Depth and Single Color Image

Title 3dDepthNet: Point Cloud Guided Depth Completion Network for Sparse Depth and Single Color Image
Authors Rui Xiang, Feng Zheng, Huapeng Su, Zhe Zhang
Abstract In this paper, we propose an end-to-end deep learning network named 3dDepthNet, which produces an accurate dense depth image from a single pair of sparse LiDAR depth and color image for robotics and autonomous driving tasks. Based on the dimensional nature of depth images, our network offers a novel 3D-to-2D coarse-to-fine dual densification design that is both accurate and lightweight. Depth densification is first performed in 3D space via point cloud completion, followed by a specially designed encoder-decoder structure that utilizes the projected dense depth from 3D completion and the original RGB-D images to perform 2D image completion. Experiments on the KITTI dataset show our network achieves state-of-art accuracy while being more efficient. Ablation and generalization tests prove that each module in our network has positive influences on the final results, and furthermore, our network is resilient to even sparser depth.
Tasks Autonomous Driving, Depth Completion
Published 2020-03-20
URL https://arxiv.org/abs/2003.09175v1
PDF https://arxiv.org/pdf/2003.09175v1.pdf
PWC https://paperswithcode.com/paper/3ddepthnet-point-cloud-guided-depth

A Novel Approach Towards Identification of Alcohol and Drug Induced People

Title A Novel Approach Towards Identification of Alcohol and Drug Induced People
Authors Joyjit Chatterjee, Anita Thakur, Vajja Mukesh
Abstract The paper proposes a novel approach towards identification of alcohol and drug induced people, through the use of a wearable bracelet.As alcohol and drug induced human people are in an unconscious state of mind, they need external help from the surroundings.With proposed Bracelet system we can identify the alcohol and drug indused people and warning trigger message is sent to their care takers. There is a definite relationship between an individual’s Blood Alcohol Content (BAC) and Pulse Rate to identify the alcohol or drug consumed person .This relationship of pulse rate with BAC is sensed by piezoelectric sensor and warning system is developed as a Bracelet device . The viability of the Bracelet is verified by Simulating a Database of 199 People’s BAC and Pulse Rate Features and classification is done among the Alcohol Induced and Normal People. For classification,Ensemble Boosted Tree Algorithm is used which is having 81.9% accuracy in decision.
Published 2020-01-14
URL https://arxiv.org/abs/2001.10344v1
PDF https://arxiv.org/pdf/2001.10344v1.pdf
PWC https://paperswithcode.com/paper/a-novel-approach-towards-identification-of
comments powered by Disqus